Where Are You? Localization from Embodied Dialog
This addresses the challenge of embodied AI localization via dialog, providing a new dataset and baseline for cooperative tasks, but it is incremental as it builds on existing dialog and localization methods.
The paper tackles the problem of localizing an agent in a 3D environment through dialog, introducing the WAY dataset with ~6k dialogs and focusing on the LED task, where their best model achieves 32.7% success within 3m compared to 70.4% for humans.
We present Where Are You? (WAY), a dataset of ~6k dialogs in which two humans -- an Observer and a Locator -- complete a cooperative localization task. The Observer is spawned at random in a 3D environment and can navigate from first-person views while answering questions from the Locator. The Locator must localize the Observer in a detailed top-down map by asking questions and giving instructions. Based on this dataset, we define three challenging tasks: Localization from Embodied Dialog or LED (localizing the Observer from dialog history), Embodied Visual Dialog (modeling the Observer), and Cooperative Localization (modeling both agents). In this paper, we focus on the LED task -- providing a strong baseline model with detailed ablations characterizing both dataset biases and the importance of various modeling choices. Our best model achieves 32.7% success at identifying the Observer's location within 3m in unseen buildings, vs. 70.4% for human Locators.